© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64384
    Prev
    Next
    INDEX
    Explanations

    extract or recover information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     implementing
    -0.99
     putting
    -0.96
    　　[
    -0.95
     with
    -0.91
    nir
    -0.90
     maximizing
    -0.90
     Photographie
    -0.89
    kset
    -0.86
     seeing
    -0.85
     variar
    -0.85
    POSITIVE LOGITS
     capture
    1.52
     captures
    1.22
     handle
    1.19
     captured
    1.14
    capture
    1.09
     recover
    1.07
     exploit
    1.06
     borrow
    1.05
    Capture
    1.05
    学习
    1.04
    Activations Density 0.094%

    No Known Activations